A new era of biological research has been unlocked, with an artificial intelligence predicting the 3D shape of nearly everyProtein known to science just one year after its first data release
More than 200 millionProtein structures have been uploaded to a free-to-access database, called AlphaFoldDB, thanks to AlphaFold.
The way for scientific exploration into the building blocks of life was paved by the achievement. Researchers are excited.
"Determining the 3D structure of a protein used to take many months or years, but it now takes seconds," Eric Topol said.
We can expect more biological mysteries to be solved each day with the addition of this new structure.
The first AlphaFold predictions were unveiled by DeepMind in July of last year.
AlphaFold is a tool that would transform biological research and speed up drug discovery.
The long proteins that are folded into pleats are linked together in a chain.
Scientists can get a better idea of how a givenprotein works by understanding its shape.
More than 200 million predicted structures of proteins found in plants, animals, and other organisms were predicted by AlphaFold.
The chief executive of DeepMind said in a statement that the hope has become a reality quicker than they had dared to dream.
A big day for #AI in life science. Release of >200 million predicted 3D protein structures from open-source #AlphaFold, nearly the entire protein universe
See: https://t.co/gjASHqACqa @DeepMind
my comment below pic.twitter.com/yPgtPHMZac
— Eric Topol (@EricTopol) July 28, 2022
Researchers have already used AlphaFold's first set of predictions to refine their understanding of deadly diseases such as Malaria, open the door to improved vaccines, and uncover biological mysteries that have stumped scientists for decades.
It's also possible to identify enzymes that could help up-cycle plastic pollution.
Sameer Velankar is a structural Biologist who heads up the EMBL-EBI'sProtein Data Bank.
Over the past year, there have been over a thousand scientific articles on a broad range of research topics using AlphaFold structures.
The impact of 1 million predictions is what's happening. Imagine the impact of having over 200 million predictions open to the public.
Although the open-source AlphaFold software has been available to researchers since its release last year, having millions of predictedProtein structures in a database will undoubtedly expedite research.
One-third of the predictions have been classified as highly accurate, on par with the structures derived from the usual experimental methods.
Scientists have painstakingly inferred the structures from the fuzzy pictures these methods produce for decades.
It is possible that AlphaFold's predictions are less accurate than scientists know. Predicted structures could be used to make sense of the data.
There is still a lot of life that AlphaFold doesn't capture.
Even though scientists have cataloged only a tiny fraction of all life on Earth, the organisms identified from traces of genetic material in soil and seawater represent an undiscovered resource.
The accessibility of the AlphaFold database and its staggering 23 terabytes of contents, which might be less feasible for some research teams to access given the costly computer power and cloud-based storage sophisticated data analyses would demand, has caused some scientists to raise concerns.
The benefits to human health that DeepMind has carefully weighed against potential bioethical risks are almost unimaginable.
Dame Janet Thornton, senior scientist at the EMBL-EBI, told The Guardian that she expected the latest update to lead to an "avalanche of new and exciting discoveries" in the months and years to come. The data are open for everyone to use.
The AlphaFold database will be refreshed frequently. You can read more about the past discoveries here.
All Rights Reserved © 2024
